INDEX

Explanations

references to national parks

oai_token-act-pair · gpt-3.5-turbo

mentions of national parks

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jad

-0.80

poll

-0.79

Bey

-0.75

Accessory

-0.69

lip

-0.67

 Benz

-0.63

âĤ¬

-0.63

auc

-0.63

demand

-0.62

devices

-0.62

POSITIVE LOGITS

conservancy

0.98

querque

0.91

 Refuge

0.85

 Sanctuary

0.82

 Conservation

0.79

 Wilderness

0.77

 Recreation

0.77

 Preservation

0.76

 wildlife

0.76

 ranger

0.73

Activations Density 0.050%

references to national parks

mentions of national parks

No Comments

No Known Activations